DeBERTaV3_model

This model is a fine-tuned version of microsoft/deberta-v3-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1419
• Accuracy: 0.9615
• F1: 0.8400
• Precision: 0.875
• Recall: 0.8077

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 5
• eval_batch_size: 5
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	1.0	26	0.3810	0.875	0.0	0.0	0.0
No log	2.0	52	0.3740	0.875	0.0	0.0	0.0
No log	3.0	78	0.3303	0.875	0.0	0.0	0.0
No log	4.0	104	0.2997	0.875	0.0	0.0	0.0
No log	5.0	130	0.2484	0.8894	0.2581	0.8	0.1538
No log	6.0	156	0.1951	0.9375	0.6977	0.8824	0.5769
No log	7.0	182	0.1752	0.9423	0.7273	0.8889	0.6154
No log	8.0	208	0.1582	0.9519	0.7917	0.8636	0.7308
No log	9.0	234	0.1449	0.9615	0.8400	0.875	0.8077
No log	10.0	260	0.1419	0.9615	0.8400	0.875	0.8077

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1